Yuwen Xiong

papers

800

total citations

papers (11)

PolyTransform: Deep Polygon Transformer for Instance Segmentation

CVPR 2020arXiv

196

citations

Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applications

CVPR 2024arXiv

148

citations

Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion

ICLR 2024arXiv

citations

Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy

ICCV 2025arXiv

citations

Rethinking Closed-Loop Training for Autonomous Driving

ECCV 2022arXiv

citations

Towards Unsupervised Object Detection From LiDAR Point Clouds

CVPR 2023arXiv

citations

Self-Supervised Representation Learning From Flow Equivariance

ICCV 2021arXiv

citations

LangBridge: Interpreting Image as a Combination of Language Embeddings

ICCV 2025arXiv

citations

Yuwen Xiong

papers (11)

PolyTransform: Deep Polygon Transformer for Instance Segmentation

Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applications

Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion

Learning Compact Representations for LiDAR Completion and Generation

LoCo: Local Contrastive Representation Learning

Weakly-supervised 3D Shape Completion in the Wild

Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy

Rethinking Closed-Loop Training for Autonomous Driving

Towards Unsupervised Object Detection From LiDAR Point Clouds

Self-Supervised Representation Learning From Flow Equivariance

LangBridge: Interpreting Image as a Combination of Language Embeddings

papers (11)

PolyTransform: Deep Polygon Transformer for Instance Segmentation

Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applications

Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion

Learning Compact Representations for LiDAR Completion and Generation

LoCo: Local Contrastive Representation Learning

Weakly-supervised 3D Shape Completion in the Wild

Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy

Rethinking Closed-Loop Training for Autonomous Driving

Towards Unsupervised Object Detection From LiDAR Point Clouds

Self-Supervised Representation Learning From Flow Equivariance

LangBridge: Interpreting Image as a Combination of Language Embeddings